TEST #1433 RESULTS
08/27/2025 - 7:00 PM
ACCELERATOR
MODEL
75.6
tokens/s
generation
1.05
sec
time to first token
1122
tokens/s
prompt
432
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:29 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1454
tokens/s
88.3
tokens/s
716
ms
pp4096+tg256
1227
tokens/s
52.0
tokens/s
3.36
sec
pp2048+tg256
1384
tokens/s
67.8
tokens/s
1.49
sec
pp2048+tg768
1257
tokens/s
64.3
tokens/s
1.64
sec
pp1024+tg1024
1321
tokens/s
75.9
tokens/s
787
ms
pp1280+tg3072
1330
tokens/s
61.7
tokens/s
976
ms
pp384+tg1152
1243
tokens/s
86.4
tokens/s
319
ms
pp64+tg1024
672
tokens/s
94.4
tokens/s
105
ms
pp16+tg1536
213
tokens/s
89.9
tokens/s
84
ms